Encyclopedia of the Sciences of Learning

2012 Edition
| Editors: Norbert M. Seel

Associative Memory and Learning

  • Friedrich T. Sommer
Reference work entry
DOI: https://doi.org/10.1007/978-1-4419-1428-6_375



Associative memories are neural networks (NNs) for modeling the learning and retrieval of memories in the brain. The retrieved memory and its query are typically represented by binary, bipolar, or real vectors describing patterns of neural activity. Learning consists of modifying the strengths of synaptic connections between neurons in the network so that neural activity can flow from memory queries to memory contents. During memory retrieval, the query pattern sets the initial activity in the neural network and the memory content is represented by the activity pattern emerging from the activity flow through the synaptic connections. Associative memories permit error-tolerant retrieval; that is, a memory can be recalled not only by the exact original query used during learning, but by all input patterns that are similar to the original...

This is a preview of subscription content, log in to check access.


  1. Amit, D. J. (1992). Modelling brain function: The world of attractor neural networks. Cambridge: Cambridge University Press.Google Scholar
  2. Gerstner, W. (2002). Spiking neuron models: Single neurons, populations, plasticity. Cambridge: Cambridge University Press.Google Scholar
  3. Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Aacademy of Sciences USA, 79, 2554–2558.Google Scholar
  4. Hopfield, J. J. (1984). Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences USA, 81, 3088–3092.Google Scholar
  5. Knoblauch, A., Palm, G., Sommer, F. T. (2010). Memory capacities for synaptic and structural plasticity. Neural Computation, 22, 289–341.Google Scholar
  6. Kohonen, T. (1984). Self-organization and associative memory. Berlin: Springer.Google Scholar
  7. Kosko, B. (1988). Bidirectional associative memories. IEEE Transactions on Systems, Man, and Cybernetics, 18(1), 49–60.Google Scholar
  8. Willshaw, D. J., Buneman, O. P., & Longuet-Higgins, H. C. (1969). Non-holographic associative memory. Nature, 222, 960–962.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Friedrich T. Sommer
    • 1
  1. 1.Redwood Center for Theoretical Neuroscience, University of CaliforniaBerkeleyUSA